Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16988
    Prev
    Next
    INDEX
    Explanations

    words related to sports, specifically related to Redknapp

    oai_token-act-pair · gpt-3.5-turbo

    specific patterns in sports-related terminology, particularly focusing on team names and their context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hran
    -0.72
    schild
    -0.64
    ashtra
    -0.62
    TAG
    -0.61
    urst
    -0.60
     Sabha
    -0.60
     Kus
    -0.59
     gol
    -0.59
    lass
    -0.57
    merce
    -0.57
    POSITIVE LOGITS
    oxide
    0.78
    tein
    0.61
    rings
    0.60
    ĪĴ
    0.60
     Tide
    0.59
     Acquisition
    0.58
    entials
    0.58
     Chili
    0.57
    ications
    0.57
    asion
    0.57
    Activations Density 0.095%

    No Known Activations